Abstract: A neural network based method places flexible blocks on a chip canvas in an integrated circuit (IC) design. The neural network receives an input describing geometric features of a flexible block to be placed on the chip canvas. The geometric features includes an area size and multiple aspect ratios. The neural network generates a probability distribution over locations on the chip canvas and the aspect ratios of the flexible block. Based on the probability distribution, a location on the chip canvas is selected for placing the flexible block with a chosen aspect ratio.

Abstract: A neural network is used to place macros on a chip canvas in an integrated circuit (IC) design. The macros are first clustered into multiple macro clusters. Then the neural network generates a probability distribution over locations on a grid and aspect ratios of a macro cluster. The grid represents the chip canvas and is formed by rows and columns of grid cells. The macro cluster is described by at least an area size, aspect ratios, and wire connections. Action masks are generated for respective ones of the aspect ratios to block out a subset of unoccupied grid cells based on design rules that optimize macro placement. Then, by applying the action masks on the probability distribution, a masked probability distribution is generated. Based on the masked probability distribution, a location on the grid is selected for placing the macro cluster with a chosen aspect ratio.

Abstract: A deep trench isolation structure including a deep trench disposed within a substrate to surround an active area on the substrate and a dielectric material filled within the deep trench. The deep trench comprises at least a corner in an arc shape layout or in a polygonal line shape layout. Accordingly, the deep trench isolation structure can be obtained in a better stress condition and with less process time for trench filling.

Abstract: A semiconductor wafer includes a silicon substrate, an active area positioned on the silicon substrate, and a field oxide layer positioned on the surface of the silicon substrate surrounding the active area. The present invention forms a doped area in the silicon substrate and within the active area and then deposits a dielectric layer on the surface of the semiconductor wafer. A dry etching process is performed to remove the dielectric layer. The top power of the dry etching process ranges between three hundred and five hundred watts to prevent damage to the silicon substrate near the field oxide layer and within the active area by the dry etching process, and to reduce the leakage current of the doped area. Additionally, the present invention also uses a wet etching process to remove the dielectric layer, which prevents an anisotropic physical impact on the silicon substrate near the field oxide layer to reduce the leakage current of the doped area.